Workflow TTS playback node filtering issue. #6877
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…g voices; 2. The bug that the front-end tts loading status must be displayed after the HTTP request is completed; 3. The bug that the front-end console errors when switching voices and the voice does not exist.
…and the TTS auto-play feature is enabled, then the output of each LLM node will play the LLM. This may not be what the user needs. This fix is to ensure that TTS only plays the text content of the output from the end node, so that whatever the user sees, TTS will play.
dosubot
bot
added
size:S
|
What will happen if this workflow has multiple branches and |
dosubot
bot
added
size:M
Regardless of whether there are multiple workflows or multiple answer nodes, the final output of the program is definitely a single answer node. At this point, the TTS should play the output content of this answer node, which is considered reasonable. This way, what the user hears should match what they see. |
|
I am currently working on improving in this direction, and I have already tested it. If you have any new issues, I hope we can communicate more. |
cuiks
pushed a commit
to cuiks/dify
that referenced
this pull request
Aug 6, 2024
ZhouhaoJiang
added a commit
that referenced
this pull request
Aug 6, 2024
* refs/heads/feat/web-app-sso: feat: web sso app Fixed a bug where permission was clearly displaye… (#6934) fix: The permissions issue of the editor role accessing some backend … (#6945) Fix: tag & settings modal in dataset card in Firefox (#6953) fix: ensure db migration in docker entry script running with `upgrade-db` command for proper locking (#6946) chore: fix markdown format and one typo (#6939) fix: restore xinference secret field (#6941) Fix increase_usage of total_price in agent_runner (#6688) fix: import workflow errors (#6937) Workflow TTS playback node filtering issue. (#6877) compatible xinference reranker server (#6927) fix: workflow trace user_id error (#6932) fix: sending app trace data to other app trace provider (#6931)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Checklist:
Important
Please review the checklist below before submitting your pull request.
dev/reformat(backend) andcd web && npx lint-staged(frontend) to appease the lint godsDescription
In the workflow chat, if a workflow contains multiple LLM nodes and the TTS auto-play feature is enabled, then the output of each LLM node will play the LLM. This may not be what the user needs. This fix is to ensure that TTS only plays the text content of the output from the end node, so that whatever the user sees, TTS will play.
eg.
In such cases, TTS should only play the output of the LLM2 node, because the final output of the Answer is the data from LLM2, and what the user sees is also the data output by LLM2. Therefore, TTS should only play the data output by LLM2.
Fixes
Type of Change
Testing Instructions
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration